© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37587
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "He" and variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    55
    +0.12
    0.6%
    502
    +0.12
    0.6%
    697
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.12
    0.06
    586
    +0.12
    0.06
    139
    +0.11
    0.06
    Negative Logits
     guiActiveUnfocused
    -0.68
     cubic
    -0.67
    Reviewer
    -0.67
    tones
    -0.61
     Marketable
    -0.60
    ãĤ¤
    -0.59
    Bound
    -0.59
     miscarriage
    -0.58
     witchcraft
    -0.58
    ÙĦ
    -0.57
    POSITIVE LOGITS
    zbollah
    1.20
    resy
    1.15
     cites
    1.06
     added
    1.03
     cited
    1.00
    idi
    0.99
     likened
    0.99
     expects
    0.98
     believes
    0.98
     cautioned
    0.98
    Activations Density 0.132%

    No Known Activations